DVNDTA: a dual virtual node based heterogeneous interaction model for accurate prediction of drug-target affinity
Guoqiang Zhou, Ben Li, Weifeng Zhang, Shudi Bao, Huaming Chen, Haoran Li, Huan Wang, Jiacong Mi, Jun Shen · 2026
Read DVNDTA: a dual virtual node based heterogeneous interaction model for accurate prediction of drug-target affinity by Guoqiang Zhou, Ben Li, Weifeng Zhang, Shudi Bao, Huaming Chen, Haoran Li, Huan Wang, Jiacong Mi, Jun Shen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13520400.txt.
Description
Guoqiang Zhou and colleagues introduce in 2026 a deep learning model that predicts how tightly a drug binds its target protein, a key early step in drug discovery. Earlier models focused only on the binding pocket, which can miss wider context from the full drug and protein.
Their design adds two virtual nodes that carry global information and exchange messages with local pocket details as layers deepen. Benchmark tests across several datasets beat leading rival models on accuracy and generalisation. The feedback loop is presented as a rough mirror of how drug and target adjust to each other during binding.
Catalog record
| CREATOR | Guoqiang Zhou, Ben Li, Weifeng Zhang, Shudi Bao, Huaming Chen, Haoran Li, Huan Wang, Jiacong Mi, Jun Shen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56152 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |